© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 307
    Prev
    Next
    INDEX
    Explanations

    words relating to negative outcomes and problems

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.81
     available
    -0.59
     snippetHide
    -0.57
    available
    -0.57
     MonoBehaviour
    -0.57
     становника
    -0.56
    Hentet
    -0.56
     achieves
    -0.54
    ItemBackground
    -0.54
    зец
    -0.54
    POSITIVE LOGITS
     caused
    1.59
     Caused
    1.32
    caused
    1.27
     arising
    1.12
     causado
    1.07
     occurring
    1.06
     exacerbated
    0.99
     affecting
    0.98
     incurred
    0.98
     occasioned
    0.96
    Activations Density 4.063%

    No Known Activations